Prediction of star polygon types in islamic geometric patterns with deep learning

Name: Prediction of star polygon types in islamic geometric patterns with deep learning
Author: Aydin, M., Agirbas, Asli

İsim	Prediction of star polygon types in islamic geometric patterns with deep learning
Yazar	Aydin, M., Agirbas, Asli
Basım Tarihi:	2024-06-17
Basım Yeri	- Springer Nature
Konu	Star polygons, Deep learning, Mask rcnn, Islamic geometric patterns
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	1590-5896
Kayıt Numarası	f55a3dc5-c875-4b95-b840-c9d11814db23
Lokasyon	Architecture
Tarih	2024-06-17
Örnek Metin	Historical buildings in the Eastern world of architecture host many Islamic geometric patterns which are known as mathematically sophisticated patterns regarding their period of creation. This study focuses on the preparation of a model that can be helpful for the analysis and restoration/maintenance of these patterns. For this, a deep learning model to detect and classify star types in Islamic geometric patterns has been proposed, and the trials were evaluated. Accordingly, this study presents a database containing 5-pointed, 6-pointed, 8-pointed and 12-pointed star types. The database consists of 600 Islamic geometric patterns. A mask RCNN algorithm was trained to detect and classify star types using the prepared database. The results of the training indicate that the loss value is 0.90 and the validation loss value is 0.85. The algorithm was tested using images that it had not seen before and the results were evaluated. This paper presents a discussion on the pros and cons of the trained algorithm.
DOI	10.1007/s00004-024-00789-6
Cilt	26

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Prediction of star polygon types in islamic geometric patterns with deep learning

Yazar Aydin, M., Agirbas, Asli

Basım Tarihi 2024-06-17

Basım Yeri - Springer Nature

Konu Star polygons, Deep learning, Mask rcnn, Islamic geometric patterns

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 1590-5896

Kayıt Numarası f55a3dc5-c875-4b95-b840-c9d11814db23

Lokasyon Architecture

Tarih 2024-06-17

Örnek Metin Historical buildings in the Eastern world of architecture host many Islamic geometric patterns which are known as mathematically sophisticated patterns regarding their period of creation. This study focuses on the preparation of a model that can be helpful for the analysis and restoration/maintenance of these patterns. For this, a deep learning model to detect and classify star types in Islamic geometric patterns has been proposed, and the trials were evaluated. Accordingly, this study presents a database containing 5-pointed, 6-pointed, 8-pointed and 12-pointed star types. The database consists of 600 Islamic geometric patterns. A mask RCNN algorithm was trained to detect and classify star types using the prepared database. The results of the training indicate that the loss value is 0.90 and the validation loss value is 0.85. The algorithm was tested using images that it had not seen before and the results were evaluated. This paper presents a discussion on the pros and cons of the trained algorithm.

DOI 10.1007/s00004-024-00789-6

Cilt 26